一作ACL 2026Findings· Findings of ACL
Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
Nguyen Viet Anh · Shiqian Zhao · Gia Dao · Runyi Hu · Yi Xie · Xiaobao Wu · Anh Tuan Luu
摘要
Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite their impressive performance, the potential for stronger reasoning abilities to introduce more severe security vulne...